Skip to main content

2021 Biomedical Informatics Seminars

December 3, 2021

Sara Murray, MD, MAS, Associate Chief Medical Information Officer, Inpt. Care and Data Science, Associate Professor of Medicine, UC San Francisco Health.  "Leveraging data to transform the health system: from insights to automation."

Abstract:  Every day, we generate massive amounts of data in our Electronic Health Record (EHR) as we care for our patients. While the data allows us to communicate important clinical information to one another, it can also be used creatively to gain insight into how our health system is functioning and identify clear areas where we can improve healthcare delivery. We will discuss a broad spectrum of examples in which EHR data can be leveraged to improve quality of care for patients and experience for providers. Automation is a critically important component of this, allowing stakeholders to meaningfully engage with information while reducing manual tasks. However, when implementing highly automated solutions such as predictive analytics, it is critical that we evaluate these tools for trustworthiness. Thus, we will review real-world cases that illustrate the importance of ensuring tools implemented are both ethical and robust.

Bio: Sara Murray, MD, MAS, is an Associate Professor of Clinical Medicine and serves as Associate Chief Medical Information Officer for Inpatient Care and Data Science at UCSF Health. She also directs the Advanced Analytics and Innovation (A2I) team, which uses data science to understand and address the most pressing issues facing the health system.

Dr. Murray is a strategic health system leader for clinical informatics, digital health, and data science. She strives to leverage healthcare data in new and impactful ways that allow for improvements in quality, safety, and value for patients and experience for providers, while also working to harmonize analytics across the organization. She has a focus on predictive analytics, including evaluation of commercially available tools and algorithms for trustworthiness prior to implementation. She also works to optimize the EHR to support clinical workflows and deploy tools to improve quality and safety, partnering with stakeholders both at UCSF and partner institutions.

Dr. Murray received her BS in Chemistry from the College of William and Mary and her MD from University of California, San Francisco. She completed her internship and residency in Internal Medicine at UCSF as well as a MAS in Clinical Research and joined the Division of Hospital Medicine as faculty in 2015. She spends her clinical time caring for patients and teaching medical students and residents on the Hospital Medicine service at UCSF.

November 19, 2021

Michael Abramoff, MD, PhD, Professor of Ophthalmology and Visual Sciences, Professor of Electrical and Computer Engineering (ECE), Professor of Biomedical Engineering (BME), University of Iowa Health Care, Department of Ophthalmology and Visual Sciences.  "From Algorithm to Industry."

Bio: Michael Abramoff, MD, PhD is the Founder and Executive Chairman at Digital Diagnostics and the Robert C. Watzke, MD Professor of Ophthalmology and Visual Sciences, Professor of Electrical and Computer Engineering, and Professor of Biomedical Engineering at the University of Iowa. He is an IEEE Fellow and an ARVO Gold Fellow. He is a retina specialist, computer scientist, and entrepreneur. As an expert in machine learning and image analysis, Dr. Abramoff was one of the original developers of a widely-used open-source image analysis app, ImageJ. His research has been continuously funded since 2004 by National Eye Institute, the Veterans Administration, the Beckman Foundation and other federal, state and philanthropic funding agencies in the U.S. and Europe.

Dr. Abramoff is the Founder and Executive Chairman of Digital Diagnostics, the Autonomous AI diagnostics company that was the first in any field of medicine to get FDA clearance for an autonomous AI. In primary care, the AI system can instantaneously diagnose diabetic retinopathy and diabetic macular edema at the point of care. This device, IDX-DR, is now part of ADA’s Standard Diabetes Care and Dr. Abramoff has also developed an ethical foundation for autonomous AI that was used during the design, validation, and regulatory and payment pathways for autonomous AI. As the author of over 300 peer-reviewed publications in this field, he has been cited over 35,000 times, and is the inventor on 17 issued patents and many patent applications.

November 12, 2021

Yingcheng Sun, PhD, Postdoctoral Research Scientist, Dept. of Biomedical Informatics, Columbia University.  "Improving clinical information retrieval for evidence-based medicine.

Abstract: Practicing evidence-based medicine (EBM) is important in today’s healthcare environment because this model of care offers clinicians a way to achieve improved quality, improved patient satisfaction, and reduced costs. Results from randomized, controlled trials are the gold standard of EBM. Unfortunately, the information overload is a common barrier today for patients seeking clinical trials and for clinicians practicing evidence-based medicine. In this report, Dr. Sun will share his work on improving the search of clinical trials, patient cohort discovery and medical evidence mining using information retrieval and machine learning methods.

Bio: Dr. Yingcheng Sun is a postdoctoral research scientist in the Department of Biomedical Informatics at Columbia University in New York City. He holds a Ph.D. in Computer Science from Case Western Reserve University. His research interests include information retrieval, machine learning and software engineering with applications in large clinical information acquisition, mining and visualization that help solving important healthcare problems.

November 5, 2021

Yun (Renee) Zhang, PhD, Assistant Professor, Dept. of Informatics, J. Craig Venter Institute. "Explainable artificial intelligence (XAI) for single cell transcriptomic analysis."

Abstract: Modern biomedical research has entered a “big data” era. Recently, the rapid advancement of single cell biotechnology has led to an accelerating growth of single cell genomic data. Single cell/nucleus RNA sequencing (scRNAseq) has emerged as an essential tool for unbiased transcriptome profiling of diverse cells in heterogeneous tissue samples. Through several world-leading efforts, such as the Human Cell Atlas and the NIH BRAIN Initiative, the single cell research community has assembled scRNAseq data for millions of cells across different organs and biological systems, which forms the most fundamental cellular basis of defining and describing health and disease for human beings. Unprecedented variety of cell types have been defined based on their transcriptional profiles using data-driven approaches. In this seminar, I will present a novel bioinformatics software suite – Celligrate – for cell type characterization and integration. Celligrate consists of a random forest machine learning algorithm, called NS-Forest, for marker gene selection and a statistical algorithm, called FR-Match, for cell type matching. The open-source software tools are available at

Bio: Yun (Renee) Zhang, PhD, is an Assistant Professor in the Informatics Department at the J. Craig Venter Institute (JCVI). She received an Masters in Mathematics and Statistics from the University of Oxford, UK, and a PhD in Statistics from the University of Rochester Medical Center. She also has industrial research experience in Novartis Oncology and Mayo Clinic. Dr. Zhang’s research interest includes statistical modeling and methodology development for big data produced by advanced biotechnologies. Her recent research focus is on applying machine learning and explainable artificial intelligence (XAI) approaches to single cell transcriptomic analysis.

October 29, 2021

John Chorba, MD, Assistant Professor, Div. of Cardiology, Department of Medicine, University of California San Francisco. "Deep Learning to Detect Heart Disease via Cardiac Auscultation."

Abstract: This talk will cover the use of deep learning in the analysis of heart sounds to detect both heart murmurs and the underlying valvular diseases that cause them. We will introduce the clinical value of the heart sounds and the technologic advances that make our approach feasible. The two main goals of the talk are, first, to understand the design, implementation, and implications of our approach, and second, to recognize the potential for future clinical applications brought by the datasets generated by the technology.

Bio: John is a chemical biologist at UCSF and a practicing cardiologist at the San Francisco General Hospital. He trained under David Liu (Harvard) as an undergraduate, Sean Whelan (Harvard Medical School) as a medical student, and Kevan Shokat (UCSF) as a postdoctoral fellow. He completed his internal medicine residency at the Massachusetts General Hospital and his cardiology fellowship at UCSF. He now leads a research group focused on applying chemical and biochemical tools to study cardiometabolic disease. His highly collaborative group uses a diverse array of techniques to develop novel therapies, prosecute new therapeutic targets, and create new diagnostic modalities for heart disease and beyond.

October 22, 2021

Edward De Brouwer, MEng, PhD Candidate, Department of Electrical Engineering, KU Leuven, Leuven, Belgium.  "Machine Learning for Patient Trajectories." 

Abstract:  The abundance and systematic collection of clinical data is an opportunity for machine learning to help transforming healthcare and moving towards precision medicine. In this talk, we will focus on longitudinal clinical data and explore how new dedicated machine learning methods can contribute to improving standard of care for chronic diseases.

Bio: Edward seeks to develop machine learning models that answer clinical questions, such as: (1) personalized healthcare and enhanced diagnostics, (2) better selection of participants in clinical trials to improve the efficiency of those trials, (3) a deeper understanding of relations between pathologies, drugs and genomic information. However, historical patient records are challenging to handle, because of intrinsic properties such as time-dependence or sporadic measurements. His research develops models that rely on the modeling of hidden variables that represent an unobserved disease state. One is matrix-factorisation with dynamic latent vectors, the other is the use of recurrent neural networks (LSTMs).

October 15, 2021

Ali Torkamani, PhDDirector of Genomics and Genome Informatics, Scripps Research Translational Institute, Associate Professor, Integrative Structural and Computational Biology, Scripps Research.  "Genotype First."

Bio: Dr. Torkamani is the Director of Genomics and Genome Informatics at the Scripps Translational Science Institute and an Associate Professor at The Scripps Research Institute. Dr. Torkamani’s research centers on the use of genomic technologies to identify the genetic etiology and underlying mechanisms of human disease in order to define health risks and individualized interventions. Major focus areas include human genome interpretation and genetic dissection of novel rare diseases, prediction of disease risk via combined genetic and clinical factors, and novel sequencing-based assays as biomarkers of disease. He has authored over 100 peer-reviewed publications as well as numerous book chapters and Medscape references, and his research has been highlighted in the popular press. Dr. Torkamani’s overall vision is to decipher that code in order to understand and predict interventions that restore diseased individuals to their personal health baseline.

October 1, 2021

Travor Cohen, MBChB, PhD, FACMIProfessor, Biomedical Informatics and Medical Education, Adjunct Professor, Department of Psychiatry, University of Washington.  "New Uses for Neural Embeddings: Biomedical Applications of Recent Advances in Neural Representations of Natural Language."

Abstract: Distributed vector representations (embeddings) of words, concepts and sentences have become increasingly prevalent as a fundamental unit of analysis in Natural Language Processing (NLP) on account of their ability to support generalization, and their alignment with the fundamental representational paradigm of neural network models. This talk will cover recent work in which such neural representations are applied to biomedical informatics problems, some of which fall outside their original conception as representations of natural language. The projects to be presented span application domains from post-marketing drug surveillance to digital phenotyping, but have a common thread between them: the desirable properties of neural representations for NLP, and how these can be leveraged to solve biomedical problems.  

Bio:  Trevor Cohen, MBChB, PhD is a Professor of Biomedical Informatics at the University of Washington in Seattle. His research focuses on the development and application of methods of distributional semantics – methods that learn to represent the meaning of terms and concepts from the ways in which they are distributed in large volumes of electronic text. The resulting distributed representations (concept or word embeddings) can be applied to a broad range of biomedical problems, such as: (1) using literature-derived models to find plausible drug/side-effect relationships; (2) finding new therapeutic applications for known medications (drug repurposing); (3) modeling the exchanges between users of health-related online social media platforms; and (4) identifying phrases within psychiatric narrative that are pertinent to particular diagnostic constructs (such as psychosis). An area of current interest involves applying literature-derived distributed representations in conjunction with observational data as a basis for machine learning. More broadly, he is interested in clinical cognition – the thought processes through which physicians interpret clinical findings – and ways to facilitate these processes using automated methods. Before joining the University of Washington, he held faculty positions at Arizona State University, and at the University of Texas Health Science Center in Houston. Prior to this, and after training and practicing as a physician in South Africa, he completed his doctoral work at Columbia University in New York, with a research focus on the development of automated methods to enhance clinical comprehension in psychiatry.

June 4, 2021

Bin Zhang, PhDPfizer-Laubach Career Development Assistant Professor of Chemistry, Associate Member of the Broad Institute. Massachusetts Institute of Technology,  "Physics-guided machine learning: from genome folding to drug screening."

Abstract: Advancements in sequencing and imaging techniques have produced valuable data for the human genome. Leverage these data to improve our understanding of 3D genome organization is an active research area. In this talk, I will present physics-guided machine learning algorithms to build structural models for the genome consistent with experimental data. Our studies have provided insight into the principles of whole-genome organization and enabled de novo predictions of chromosome structures from epigenetic modifications. These algorithms are equally beneficial for analyzing datasets produced by molecular simulations to allow fast and efficient drug screening.

Bio: Bin Zhang is an assistant professor in the Chemistry department at MIT. He attended the University of Science and Technology of China (USTC) as a chemical physics major. After graduating from USTC in 2007, Bin moved to the United States to pursue doctoral research at the California Institute of Technology in Thomas Miller’s group. Upon graduation, Bin accepted a position as a postdoctoral scholar with Peter G. Wolynes at the Center for Theoretical Biological Physics at Rice University. Bin joined MIT faculty as an assistant professor in 2016. His research focuses on studying three-dimensional genome organization with interdisciplinary approaches that combine bioinformatics analysis, computational modeling and statistical mechanical theory. While at MIT, Bin has received awards that include the Scialog Fellowship and the NSF CAREER Award.

May 7, 2021

George Demiris, PhD, FACMI, PIK (Penn Integrates Knowledge) University Professor, Department of Biobehavioral Health Sciences, School of Nursing & Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania.  "Patient Engagement and the Digital Phenotype."

Abstract: Emergence of passive monitoring technologies and wearable devices have introduced digital phenotyping and behavioral sensing as approaches to understanding individuals’ behavioral patterns, environmental context and health needs. This presentation provides examples of the use of passive monitoring in gerontology and discuss practical, ethical and clinical implications of digital phenotyping as a platform to promote patient engagement and shared decision making.  

Bio: George  Demiris is a PIK (Penn Integrates Knowledge) University Professor at the University of Pennsylvania and holds joint faculty appointments in the Informatics Division of the Department of Biostatistics, Epidemiology and Informatics, Perelman School of Medicine and in the Department of Biobehavioral Health Sciences of the School of Nursing. He explores innovative ways to utilize technology and support patients and their families in various settings, including home and hospice care. He also focuses on designing and evaluating personal health systems that produce patient-generated data including “smart home” solutions for aging. He is a Member of the National Academy of Medicine, a Fellow of the American College of Medical Informatics and the Gerontological Society of America. He has conducted numerous federally funded studies and his work has been funded consistently over the years both by the National Institutes of Health (NIH) and the National Science Foundation (NSF).

April 30, 2021

Laura K. Wiley, Ph.D., Assistant Professor of Biostatistics & Informatics, University of Colorado - Anschutz Medical Campus.  "Developing an Equitable and Reproducible Learning Healthcare System."

Abstract: Every step within the learning healthcare system is dependent upon accurate identification of the patient population of interest. Just as inclusion/exclusion criteria impact the generalizability of randomized controlled trials, the algorithm used for population identification impacts the applicability and generalizability of EHR-based evidence generation. This seminar will discuss my group's effort to improve the equity and reproducibility of this process to ensure that all patients can benefit from informatics.

Bio: Dr. Laura Wiley is an Assistant Professor of Biomedical Informatics and Personalized Medicine at the University of Colorado Anschutz Medical Campus. Her work focuses on computational phenotyping and other informatics methodologies for clinical evidence generation in support of precision medicine. She is also a national leader in the American Medical Informatics Association serving as Vice Chair of both the 2019 AMIA Annual Symposium and the 2021 AMIA Informatics Summit.

April 23, 2021

Christian Dameff, M.D., M.S., Assistant Professor of Emergency Medicine, Biomedical Informatics, & Computer Science, Medical Director of Cyber Security, UC San Diego Health.  "Hacking Humanity: Patient Safety in the Era of Hyperconnected Healthcare."

Abstract: Hackers are attacking healthcare. As our reliance on unreliable technology increases, the risks to our patients may be much more than just stolen data.

Bio: Dr. Christian Dameff is an assistant professor of Emergency Medicine, Biomedical Informatics, and Computer Science (affiliate) at the University of California San Diego. At UCSD Health he was hired as the nation’s first Medical Director of Cyber Security. Published clinical works include post cardiac arrest care including therapeutic hypothermia, novel drug targets for acute myocardial infarction patients, ventricular fibrillation waveform analysis, cardiopulmonary resuscitation (CPR) quality and optimization, dispatch assisted CPR, teletoxicology, clinical applications of wearables, and electronic health records.

Dr. Dameff is also a hacker and security researcher interested in the intersection of healthcare, patient safety, and cybersecurity. He has spoken at some of the world’s most prominent Cyber Security forums including DEFCON, RSA, Blackhat, Derbycon, BSides, and is one of the cofounders of the CyberMed Summit, a novel multidisciplinary conference with emphasis on medical device and infrastructure cybersecurity. Published cybersecurity topics include hacking 911 systems, HL7 messaging vulnerabilities, and malware.

April 16, 2021

Jyoti Mishra, Ph.D., Assistant Professor of Psychiatry, Director, Neural Engineering and Translational Labs (NEATLabs), UC San Diego.  "Mapping the Cognitive Brain at Scale with Implications for Loneliness and Personalized Mental Health Care.'

Abstract: While neuroscience has made vast advances in the understanding of mental disorders, assessments in today’s mental health clinics remain subjective, i.e. based on patient symptom reports. In this talk, Dr. Mishra, who directs the Neural Engineering & Translation Labs (NEATLabs) in the department of Psychiatry, will discuss recent research efforts towards translating cognitive and computational neuroscientific methods to scalable human brain mapping tools, which are accessible to clinics. The scalability of the tools has allowed NEATLabs to rapidly collect larger samples of human data and simultaneously identify objective neuro-cognitive markers of health risk factors such as loneliness. At the end of the talk, Dr. Mishra will describe how NEATLabs is using the cognitive brain mapping tools integrated with real-world assessments from wearables to advance N-of-1 mental health care.

Bio: Dr. Mishra is trained in both cognitive and computational neurosciences, with expertise in studies of attention, learning and brain plasticity. She has contributed to technology innovations in immersive cognitive assessments and closed-loop interactive games. At NEATLabs, she leads innovation of neuro-technologies for mental health diagnoses and precision therapeutics.

April 9, 2021

Smruthi Karthikeyan, Ph.D., Postdoctoral Researcher, Department of Pediatrics, UC San Diego.  "Implementation of large-scale wastewater surveillance in tracking COVID-19 infection dynamics."

Bio:   Smruthi obtained her PhD in Environmental Engineering from Georgia Institute of Technology in Dec 2019, mainly specializing in environmental microbial genomics, working at the interface of microbial ecology, computational biology and engineering. As a part of her PhD thesis, Smruthi worked on developing integrated wet-lab and computational biology based approaches to model, predict and forecast ecosystem recovery patterns in benthic ecosystems affected by the 2010 Deepwater Horizon oil spill. Smruthi joined the Knight lab in March 2020 and is interested in using multi-omics approaches to provide a holistic view of environmental systems.

April 2, 2021

Jihoon Kim, M.S., Principal Statistician, UCSD Health Dept. of Biomedical Informatics.  "Privacy-Protecting, Reliable Response Data Discovery Using COVID-19 Patient Observations."

Abstract:  We developed a distributed, federated network of 12 health systems that harmonized their EHRs and submitted aggregate answers to consortia questions posted at Our consortium developed processes and implemented distributed algorithms to produce answers to a variety of questions. We were able to generate counts, descriptive statistics, and build a multivariate, iterative regression model without centralizing individual-level data. Our public web site contains answers to various clinical questions, a web form for users to ask questions in natural language, and a list of items that are currently pending responses. We demonstrated that it is possible to answer questions about COVID-19 using EHR data from systems that have different policies and must follow various regulations, without moving data out of their health systems. We present an alternative or complement to centralized COVID-19 registries of EHR data. We can use multivariate distributed logistic regression on observations recorded in the process of care to generate results without transferring individual-level data outside the health systems.

March 12, 2021

Roberto Rocha, M.D., Ph.D., Managing Directory, Semedy, Inc., Assistant Professor of Medicine, Harvard Medical School.  "Knowledge Management and Informatics."

Abstract:  Healthcare organizations create and manage large amounts of knowledge assets. Despite the negative consequences of inconsistent, incomplete or outdated assets, few organizations have established systematic and coordinated knowledge management activities. Core knowledge management activities will be described using illustrative scenarios, with emphasis on informatics methods and tools that promote consistency and sustainability. Research and innovation opportunities derived from existing challenges will be outlined and discussed. 

Bio:  Dr. Rocha is the Managing Director of Semedy Inc. and an Assistant Professor of Medicine at Harvard Medical School. Prior to joining Semedy, Dr. Rocha was Clinical Informatics Director at Partners HealthCare (2008-2017), Assistant Professor of Biomedical Informatics at the University of Utah (2000-2008), and Senior Medical Informaticist at Intermountain Healthcare (2000-2006). Prior to Intermountain, Dr. Rocha was an Associate Professor of Medical Informatics at the Federal University of Paraná (1997-2000), Brazil, and CIO of the University Hospital. Dr. Rocha completed a PhD in Medical Informatics from the University of Utah and received his MD from the Federal University of Paraná. Dr. Rocha is a Fellow of the American College of Medical Informatics.

March 5, 2021

Brian Clay, M.D., Prof. of Medicine, Div. Hospital Medicine and Biomedical Informatics Chief Medical Information Officer, Inpatient and Hospital Affiliations, Associate Chief Medical Officer for Inpatient Care
UC San Diego Health and Amy M. Sitapati, M.D., Prof. of Medicine, Div. General Internal Medicine and Biomedical Informatics, Chief Medical Information Officer, Population Health, UC San Diego Health.  "Clinical Information Systems and COVID-19: An Equitable, Agile Healthcare System Response to COVID."

Bio:  Dr. Brian Clay is Clinical Professor of Medicine and a hospital medicine physician at UC San Diego Health. He serves as the Chief Medical Information Officer for the organization as well as the Associate Chief Medical Officer for inpatient care. He leads the physician informatics team at UCSD and focuses his informatics work on quality and safety, inpatient efficiency and workflow optimization, interoperability and clinical decision support. Dr. Clay completed his medical residency training at Vanderbilt University and earned his medical degree from UC San Diego School of Medicine. Dr. Clay is board-certified both in internal medicine with a recognized focus in hospital medicine and in clinical informatics.

Dr. Amy M. Sitapati is Professor of Medicine and a primary care physician at UC San Diego Health. She is Medical Director of Internal Medicine in La Jolla and leads the population health team that focuses on how clinical informatics can be used to improve the quality of care. Dr. Sitapati is nationally recognized for her work in population health informatics. She has expertise in designing registries, analytics, and population health outreach. Her areas of interest include health equity, quality, and public records. Dr. Sitapati is an investigator for the NIH All of Us program and is also an investigator for the California Integrated Vital Records. Dr. Sitapati provides primary care for adults, including preventive care and diagnosis and treatment of acute and chronic diseases. She believes that the best health is achieved through life balance, patient empowerment, a good physician-patient relationship, and integrated care. Dr. Sitapati completed her medical residency training at UC San Diego School of Medicine and earned her medical degree from Case Western Reserve University, School of Medicine. Dr. Sitapati is board-certified in internal medicine and clinical informatics.

February 26, 2021

Daniella Meeker, Ph.D.Assistant Professor, Dept. of Public and Population Health Sciences, USC Keck School of Medicine, Co-Director, Informatics Program SC-CTSI.  "Behavioral Economics and Informatics in Health Decision-Making."

Abstract:  Most models of decision-making in healthcare assume that patients and physicians are rational actors optimizing outcomes, whether financial or clinical. Studies in behavioral sciences have shown that decision-making is more complex and illogical. We conducted several randomized field experiments and observational data analyses showing the ways that behavioral science impacts the quality of care and disparities. The comparative effectiveness of different quality improvement interventions and relevant implementation details will be discussed.  

Bio: Dr. Daniella Meeker serves as a director of the Clinical Research Informatics program within the Southern California Clinical and Translational Science Institute. Before joining SC CTSI she was a System Engineer and an Information Scientist at RAND. She completed a post-doctoral fellowship at the RAND Bing Center for Health Economics. Her current research is focused on distributed architectures for data management, analysis, and translational practice. Her other work includes development of collaborative platforms for knowledge management, program evaluation, social network analysis, and applied health and behavioral economics. Dr. Meeker has served as the technical and implementation lead for two clinical data research networks funded by the National Institute on Aging and the Agency for Healthcare Research and Quality.

February 19, 2021

Robert A. Greenes, M.D., Ph.D., Emeritus Professor and Ira A. Fulton Chair in Biomedical Informatics
Arizona State University and Mayo Clinic. "Knowledge-Enhanced Health IT: Clinical Decision Support & Beyond."

Abstract: The prospect of using computers to enhance healthcare with knowledge captured academic and professional interest from its earliest days, more than six decades ago, when computer-aided diagnosis was a hot topic. Clinical decision support (CDS) – in the form of targeted information retrieval, alerts, reminders, order sets, templates for data entry and reporting, and visualizations that portray patient status or trends at a glance – have been an important part of most operational clinical systems.

However, the challenges of implementing knowledge artifacts so that they work well in different settings and with different workflows, are sufficiently patient-specific, and are able to be maintained and updated regularly have been huge. Also the negative aspects of poor use of CDS have resulted in user dissatisfaction, alert fatigue, and other complaints, and have been blamed for contributing to physician burnout. The penetration of CDS, as a result, has been far less than desirable.

Many disruptive changes in our current environment raise the possibilities of both broader range of opportunities for use of knowledge to enhance health and health care than has been achieved to date by traditional CDS methods, as well as to potentially reduce the implementation and usage challenges. These opportunities include use of context awareness, adaptation to cognitive intent and workflow, and dynamic assembly of needed resources. This talk will briefly review the history and state of the art of knowledge-enhanced health IT, and identify a set of research initiatives aimed at reimaging the approaches to this need.

Bio: Dr. Robert Greenes is Emeritus Professor and Ira A. Fulton Chair in Biomedical Informatics, Arizona State University, and Professor of Biomedical Informatics, Mayo Clinic. Now living in San Diego. Main interests have been in facilitating human-computer interaction, problem solving, and decision making in healthcare. With MD and PhD from Harvard, Board-certified in Radiology, Brigham and Women’s Hospital, he was Director, Decision Systems Group and Radiologist, Brigham and Women’s Hospital, and professor of biomedical informatics, and of healthcare policy and management, Harvard. He was the director of the Harvard/MIT research training program in biomedical informatics, for more than 20 years. Dr. Greenes was co-development of the MUMPS system in the 1960s, and has worked for many years on developing models and standards for clinical decision support. He is the author/editor of Clinical Decision Support (now in 2nd Edition): The Road to Broad Adoption, Elsevier, 2014, with a third edition now underway. He is a Member of the National Academy of Medicine; and Fellow, American College of Medical Informatics, American College of Radiology, Society of Imaging Informatics in Medicine; and International Academy of Health Science Informatics. He was the 2008 recipient of the Morris F. Collen Award in biomedical informatics, American College of Medical Informatics. The Robert A. Greenes Directorship in Biomedical Informatics was established, 2007, at Brigham and Women’s Hospital, and continues to bear his name.

February 12, 2021

Jessilyn Dunn, Ph.D., Assistant Professor, Dept of Biomedical Engineering, Duke University.  "Precision Health Through Multi-scale and Multi-Modal Biomedical Data Integration."

Abstract: Recent technological advancements make it possible to closely and continuously monitor individuals on multiple scales in real time while also incorporating genetic, environmental, and lifestyle information. We are collecting and using this multi-scale biomedical data to gain a more precise understanding of health and disease at molecular and physiological levels and developing actionable, predictive health models for improving health outcomes. We are simultaneously developing tools for the digital health community, including the Digital Biomarker Discovery Pipeline (DBDP), to facilitate the use of mobile device data in healthcare.   

Bio: Dr. Jessilyn Dunn is an Assistant Professor of Biomedical Engineering and Biostatistics & Bioinformatics at Duke University. Her primary areas of research focus on biomedical data science and mobile health; her work includes multi-omics, wearable sensor, and electronic health records integration and digital biomarker discovery. Dr. Dunn is the Director of the BIG IDEAs Laboratory, whose goal is to detect, treat, and prevent chronic and acute diseases through digital health innovation. She is also currently PI of the CovIdentify study to detect and monitor COVID-19 using mobile health technologies. Dr. Dunn was an NIH Big Data to Knowledge (BD2K) Postdoctoral Fellow at Stanford and an NSF Graduate Research Fellow at Georgia Tech and Emory, as well as a visiting scholar at the US Centers for Disease Control and Prevention and the National Cardiovascular Research Institute in Madrid, Spain. Her work has been internationally recognized with media coverage from the NIH Director’s Blog to Wired, Time, and US News and World Report.

February 5, 2021

Shumei Kato, M.D.Associate Professor of Medicine, Gastrointestinal and Experimental Therapeutics Program, UCSD Moores Cancer Center.  "Genomics and Immunotherapy Making Matched Targeted Combination Approach a Clinical Reality."

Abstract: Although targeted therapies and immunotherapies can demonstrate salutary anti-cancer effect in portion of patients, unfortunately many tumors show resistance to cognate mono-therapies, and majority of patients who do respond eventually develop resistance. Factors that may limit response to matched targeted mono-therapies include genomic heterogeneity and complexity, as well as the fact that most patients with advanced malignancy often harbor distinct molecular profiles (as in the case with snowflakes). Moreover, understanding molecular findings and accessing drugs/clinical trials can be challenging. To implement a precision medicine strategy, we initiated a multidisciplinary molecular tumor board with a goal of developing N-of-One treatments that could be initiated by the physician under the auspices of a master protocol (UCSD-PREDICT study, NCT02478931). Preliminary results to date show that implementation of tissue next-generation sequencing, cell-free DNA assay, transcriptomic and immunohistochemistry to guide personalized/customized matched targeted therapy approach is feasible and can improve clinical outcomes including progression-free survival and overall survival. Representative patient cases managed with personalized/customized targeted therapy approach will be discussed. 

Bio: Dr. Shumei Kato is Associate Clinical Professor at the Gastrointestinal and Experimental Therapeutics program, UCSD Moores Cancer Center. Dr. Kato’s research interest has been the identification of molecular targets among patients with diverse cancers, as well as to identify the response/resistance mechanism from targeted and/or immunotherapeutic agents, that may be transformed into patient care.

January 29, 2021

Raymond J King, Ph.D., MSc, Senior Advisor for Informatics, Division of Nutrition, Physical Activity, and Obesity, National Center for Chronic Disease Prevention and Health Promotion, Centers for Disease Control and Prevention (CDC).  "Childhood Obesity Data Initiative (CODI): Integrating Clinical and Community Data for Population Health."

Abstract: Childhood obesity impacts almost 14 million children in the U S and is associated with serious immediate and long-term problems including poor mental and physical health outcomes and lower academic achievement. Research that assesses childhood obesity interventions is limited because researchers cannot easily link pediatric health-related data stored across different health information systems. The U.S. Centers for Disease Control and Prevention (CDC) is leading the Childhood Obesity Data Initiative (CODI) to leverage existing information technology tools to facilitate data access.  CODI will build on the existing, clinically focused Patient-Centered Outcomes Research Network (PCORnet) Common Data Model (CDM) by piloting -through the addition of ancillary tables to the CDM-improved access to social determinants of health, geographic risk markers, and information about participation in clinical and community weigh management programs. CODI will implement privacy preserving record linkage across health information systems and community-based programs protecting individuals' personally-identifiable information. CODI will be piloted in Denver, Colorado using the Colorado Health Observation Regional Data Service (CHORDS).   

Bio: Dr. King (Ray) is an epidemiologist and informaticist and Senior Advisor for Informatics in the Division of Nutrition, Physical Activity, and Obesity, National Center for Chronic Disease Prevention and Health Promotion, Centers for Disease Control and Prevention (CDC). He leads projects investigating the utility of EHR data for obesity population health and surveillance and co-leads the CDC Childhood Obesity Data Initiative (CODI) effort developing methods, tools and services for integrating multisector data for obesity population health. He has 20 years of experience at CDC with an interest in informatics, spatial epidemiology, and a systems approach to understanding the distribution and determinants of disease and the development of multisector solutions for population health prevention and control. Ray is a graduate of CDC’s Public Health Informatics Fellowship and Emerging Infectious Diseases Fellowship. He received a PhD in Epidemiology and MSc in the Control of Infectious Diseases from the London School of Hygiene and Tropical Medicine and a BA from Emory University.

January 22, 2021

Xinzhi Zhang, M.D., Ph.D., FACE, FRSMProgram Director, National Center for Data to Health (CD2H); Lead, Rural Health and Health Equity; Lead, Diversity and Re-entry Supplements; Clinical and Translational Science Awards (CTSA) Program; Division of Clinical Innovation; National Center for Advancing Translational Sciences, NIH.  "Big Data, Small Populations - A Conversation on Translational Health Equity Research."

Abstract:  With deliberate efforts, Big Data presents a dramatic opportunity for reducing health disparities but without active engagement, it risks further widening them. This conversation will focus on challenges and opportunities that Big Data science may offer to the reduction of health and health care disparities.   

Bio: Xinzhi Zhang is a program director in the NCATS Division of Clinical Innovation, where he manages a portfolio of Clinical and Translational Science Awards (CTSA), including the CTSA National Center for Data to Health. He is also a lieutenant commander in the U.S. Public Health Service Commissioned Corps, an elite group of public health leaders who respond to national health crises.

Dr. Zhang joined NIH in 2012 as a program director in the National Institute on Minority Health and Health Disparities’ Division of Extramural Scientific Programs where he provided leadership for scientific program development and project management on minority health and health disparities research. Prior to that, Zhang had joined the National Center for Infectious Diseases’ Office of Surveillance at the Centers for Disease Control and Prevention (CDC) in 2003 as a Steven M. Teutsch Prevention Effectiveness Fellow. From 2005 to 2012, he was an epidemiologist in CDC’s National Center for Chronic Disease Prevention and Health Promotion’s Division of Diabetes Translation. Dr. Zhang has authored papers for inclusion in CDC’s Morbidity and Mortality Weekly Report, as well as book chapters, and he has had more than 60 articles published in peer-reviewed journals, including the Journal of the American Medical Association, the American Journal of Public Health and the American Journal of Preventive Medicine. Currently, he also serves as an associate editor of Health Equity(link is external).

Zhang received his M.D. from Peking Union Medical College in 1998 and his Ph.D. in health services administration from the University of Alabama at Birmingham in 2003.

January 15, 2021

Tsung-Ting (Tim) Kuo, Ph.D.Assistant Professor, UCSD Health Department of Biomedical Informatics, University of California San Diego.  "Decentralized Predictive Modeling on Blockchain."

Abstract: In this talk, Dr. Tsung-Ting Kuo will introduce decentralized predictive modeling, healthcare blockchain, and how these two technologies can be combined to preserve privacy for collaborative machine learning. He will also discuss other use cases of healthcare blockchain.   

Bio: Dr. Tsung-Ting Kuo is an Assistant Professor of Medicine in University of California San Diego (UCSD) Health Department of Biomedical Informatics (DBMI). He earned his PhD from National Taiwan University (NTU) in the Institute of Networking and Multimedia. Prior to becoming a faculty member, he was a Postdoctoral Scholar at UCSD DBMI and received the UCSD Chancellor’s Outstanding Postdoctoral Scholar Award. He was a major contributor towards the UCSD DBMI team winning the Office of the National Coordinator for Health Information Technology (ONC) healthcare blockchain challenge, and also the NTU team winning the Association for Computing Machinery (ACM) Knowledge Discovery and Data Mining (KDD) Cup competition four times. He was awarded a NIH K99/R00 Pathway to Independence Award with an Administrative Supplement, as well as UCSD Academic Senate Health Science Research Grant and Travel Award, for blockchain-based biomedical, healthcare and genomic studies. His research focuses on blockchain technologies, machine learning, and natural language processing.

January 8, 2021 

Julia Adler-Milstein, Ph.D., Professor of Medicine, Director of the Center for Clinical Informatics and Improvement Research, UCSF.  "Turning Digital Fumes into a Breath of Fresh Air." 

Abstract:  While EHR data is heavily used for clinical research, there is also significant potential for behavioral and social science research. In my talk, I will describe EHR access logs as a novel source of data that captures individual and team behaviors, and give examples of how such data can be applied to address policy- and practice-based questions related to user interface design, clinician burnout, and clinical workflow.   

Bio:  Dr. Julia Adler-Milstein is a Professor of Medicine and Director of the Center for Clinical Informatics and Improvement Research (CLIIR). Dr. Adler-Milstein is a leading researcher in health IT policy, with a specific focus on electronic health records and interoperability. She has examined policies and organizational strategies that enable effective use of electronic health records and promote interoperability. She is also an expert in EHR audit log data and its application to studying clinician behavior. Her research – used by researchers, health systems, and policymakers – identifies obstacles to progress and ways to overcome them.

She has published over 100 influential papers, testified before the US Senate Health, Education, Labor and Pensions Committee, is a member of the National Academy of Medicine, been named one of the top 10 influential women in health IT, and won numerous awards, including the New Investigator Award from the American Medical Informatics Association and the Alice S. Hersh New Investigator Award from AcademyHealth. She has served on an array of influential committees and boards, including the NHS National Advisory Group on Health Information Technology, the Health Care Advisory Board for Politico, and the Interoperability Committee of the National Quality Forum.

Dr. Adler-Milstein holds a PhD in Health Policy from Harvard and spent six years on the faculty at University of Michigan prior to joining UCSF as a Professor in the Department of Medicine and the inaugural director of the Center for Clinical Informatics and Improvement Research.